game-unity-specialist
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided questions or tasks concerning Unity development. This input serves as the primary driver for the agent's actions, including code generation and project analysis.
- Ingestion points: User input is ingested via the
argument-hintas defined in the frontmatter and used throughout the "Your Workflow" section to guide responses. - Boundary markers: Absent. There are no explicit delimiters or instructions provided to the model to treat user-supplied input as untrusted or to ignore potentially malicious instructions embedded within user questions.
- Capability inventory: The skill possesses significant capabilities via its
allowed-tools, includingRead,Write,Edit, andBash. These could be leveraged if the agent were manipulated by an indirect prompt injection. - Sanitization: Absent. The instructions do not mandate any validation or sanitization of user-provided content or file contents before the agent operates on them.
Audit Metadata